Annotation-Guided Temporal Attention with a Sleep Foundation Model for Predicting Future Cognitive Impairment from Polysomnography

Xiao-Yun Wang Wei-Ping Liu Yi-Xuan Zhang Jia-Wei Wu Bi-Han Chi Yi Fu Xiaojun Ning Jing Wang David C. Wong

· 0 citations · 8 references

TL;DR

A complete prediction pipeline was developed that used a frozen SleepFM encoder for five-minute PSG segments, a bidirectional LSTM for temporal modelling, and annotation-guided attention based on algorithmic sleep stages and events for future cognitive-impairment prediction.

Semantic Scholar

View source

Similar papers

Predicting Future Cognitive Impairment from Sleep EEG with a Lightweight Convolutional Network

Shyamal Y. Dharia, Stephen D. Smith, Camilo E. Valderrama · 0 citations

Frozen SleepFM and engineered polysomnographic features for prediction of subsequent cognitive impairment diagnoses

Karen K. Wurzel, D. Kaftan, M. Du Pont et al. · 0 citations

Transfer Learning from a Multimodal Sleep Foundation Model for Cognitive Impairment Prediction Using Polysomnography and Clinical Features

Jing-Ming Zhang, Zi-Jie Zhu, Chao-Yu Wei et al. · 0 citations

Predicting Future Cognitive Impairment Using Whole-Night Sleep-Derived Outcomes

F. Ehrlich, Sara B. ̈acker, Alex Schmidt et al. · 0 citations

Predicting Cognitive Impairment from Polysomnography with Tabular Foundation Model and Markov Transition Matrix

Kelvin K. Nguyen, Arshia Ilaty, A. Smithwick et al. · 0 citations

Deep Learning of Multimodal Features Derived from Raw Polysomnography for Cognitive Impairment Prediction

The results support the potential of routine polysomnography for opportunistic cognitive-risk assessment and fused the epoch-level features with whole-night aggregated features and demographics using a temporal convolutional network for binary prediction of cognitive impairment.

Somesh Saini, S. Thanaviratananich, M. Araujo · 0 citations